© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98156
    Prev
    Next
    INDEX
    Explanations

    academic assignments and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spiritu
    -1.02
     steen
    -0.93
     luxem
    -0.93
     jao
    -0.88
     philippe
    -0.88
     praktik
    -0.85
     mü
    -0.84
    riotic
    -0.84
     kapas
    -0.82
     fabrik
    -0.79
    POSITIVE LOGITS
    assignment
    1.41
     assignment
    1.38
    Assignment
    1.36
     essay
    1.30
     Assignment
    1.25
    essay
    1.18
     Numerade
    1.10
    作业
    1.08
    Essay
    1.05
     coursework
    1.05
    Activations Density 0.017%

    No Known Activations